mlgym-bench@1.0

Evaluates agents on ML tasks across computer vision, RL, tabular ML, and game theory.

← Back to Registry

Run this task

CLI:

inspect eval inspect_harbor/mlgym_bench_1_0 --model openai/gpt-5

Python:

from inspect_ai import eval
from inspect_harbor import mlgym_bench_1_0

eval(mlgym_bench_1_0(), model="openai/gpt-5")

Dataset information

Harbor registry	mlgym-bench@1.0
Inspect task	mlgym_bench_1_0
Version	1.0
Samples	12
Paper	arxiv

See Task Parameters for the parameter set shared across all Harbor tasks.